Qwen2.5 Coder 7B

qwen • qwen-2-5-coder-7b-instruct

Model Information

Slug	qwen-2-5-coder-7b-instruct
LLMs.txt	View
Release Date	September 19, 2024

Organization

Name	qwen
Website	https://qwen.ai/

Model Description

Qwen2.5-Coder-7B-Instruct is a 7B parameter instruction-tuned language model optimized for code-related tasks such as code generation, reasoning, and bug fixing. Based on the Qwen2.5 architecture, it incorporates enhancements like RoPE, SwiGLU, RMSNorm, and GQA attention with support for up to 128K tokens using YaRN-based extrapolation. It is trained on a large corpus of source code, synthetic data, and text-code grounding, providing robust performance across programming languages and agentic coding workflows.

This model is part of the Qwen2.5-Coder family and offers strong compatibility with tools like vLLM for efficient deployment. Released under the Apache 2.0 license.

Available at 6 Providers

Provider	Type	Model Name	Original Model	Input ($/1M)	Output ($/1M)	Actions
Alibaba (China)		Qwen2.5-Coder 7B Instruct	`qwen2-5-coder-7b-instruct`	$0.14	$0.29	Visit
AIHubMix	Chat Code	qwen2.5-coder-7b-instruct	`qwen2.5-coder-7b-instruct`	$0.20	$0.40	Model
Fireworks AI		Qwen2.5-Coder 7B Instruct	`qwen2p5-coder-7b-instruct`	$0.20	$0.20	Visit
LangDB		qwen2.5-coder-7b-instruct	`qwen2.5-coder-7b-instruct`	-	-	Model
Writingmate	Chat Code	Qwen: Qwen2.5 Coder 7B Instruct	`qwen/qwen2.5-coder-7b-instruct`	-	-	Model
Featherless		Qwen/Qwen2.5-Coder-7B-Instruct	`Qwen/Qwen2.5-Coder-7B-Instruct`	-	-	Visit

Back to Models View Organization